# qwen/qwen3-235b-a22b-2507 across inference providers

Reference: context 262,144 tokens from https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507/blob/ac9c66cc9b46af7306746a9250f23d47083d689e/config.json (max_position_embeddings); quantization bf16, plus an official FP8 release (Qwen/Qwen3-235B-A22B-Instruct-2507-FP8).

Provider rows: https://openrouter.ai/api/v1/models/qwen/qwen3-235b-a22b-2507/endpoints, read 2026-10-19. Declared values; no requests sent.

| Provider | Tag | Quantization | Context | Max output | Tools | Reasoning | Differs from the reference |
|---|---|---|---|---|---|---|---|
| DeepInfra | deepinfra/fp8 | fp8 (same) | 262,144 | 16,384 | yes | n/a | none declared |
| GMICloud | gmicloud/fp8 | fp8 (same) | 262,144 | 235,929 | yes | n/a | none declared |
| Google | google-vertex/us-south1 | none (undisclosed) | 262,144 | 16,384 | yes | n/a | none declared |
| Google | google-vertex/us-south1 | none (undisclosed) | 262,144 | 16,384 | no | n/a | **declares no tools parameter; the official model supports tool calling** |
| Nebius | nebius/fp8 | fp8 (same) | 262,144 | 235,929 | yes | n/a | none declared |
| Parasail | parasail/fp8 | fp8 (same) | 131,072 | 117,964 | yes | n/a | **declares a 131,072-token context; the reference config says 262,144 (50%)** |
| Venice | venice/fp8 | fp8 (same) | 128,000 | 16,384 | yes | n/a | **declares a 128,000-token context; the reference config says 262,144 (49%)** |

## Changes since tracking began

None yet.